George Cybenko

George Cybenko is the Dorothy and Walter Gramm Professor of Engineering at Dartmouth and a fellow of the IEEE.[1]

Education

Cybenko obtained his BA in mathematics from the University of Toronto and received his PhD from Princeton in applied mathematics of electrical and computer engineering in 1978.

Work

Cybenko has served as an advisor for the Defense Science Board and several other government panels and is the founding editor-in-chief of the IEEE Security & Privacy magazine. His current research interests are distributed information, control systems, and signal processing, with a focus on applications to security and infrastructure protection. He is known for proving the universal approximation theorem for artificial neural networks with sigmoid activation functions.[2]

gollark: It's not real critical infrastructure unless you have an accursed diagram.
gollark: I use a likeability inductor.
gollark: The main problem with this is that it's entirely inapplicable to Minecraft mods, because any explanation for how they *work* is just going to be "well, we put code in saying so" and tiny amounts of flavor text.
gollark: Basically, magic is natural law which runs on a different level of abstraction/ontology to real-world physics.
gollark: I did of course invent the unified gollarious theory of magic™ retroactively.

References
  1. Princeton EE alumni profiles
  2. Cybenko, G. (1989) "Approximations by superpositions of sigmoidal functions", Mathematics of Control, Signals, and Systems, 2(4), 303–314. doi:10.1007/BF02551274


This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.